An approximation theory approach to learning with \(\ell^1\) regularization

DOI10.1016/j.jat.2012.12.004zbMath1283.68308MaRDI QIDQ1944318

Hong-Yan Wang, Quan-Wu Xiao, Ding-Xuan Zhou

Publication date: 5 April 2013

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jat.2012.12.004

zbMATH Keywords

learning theory; multivariate approximation; \(\ell ^{1}\)-regularizer; data dependent hypothesis spaces; data dependent hypothesis space; \(l^1\)-regularizer multivariate approximation; kernel-based regularization scheme

Mathematics Subject Classification ID

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

41A63: Multidimensional problems

Related Items

Unnamed Item, Multikernel Regression with Sparsity Constraint, Unnamed Item, Learning with Convex Loss and Indefinite Kernels, Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels, Learning theory approach to a system identification problem involving atomic norm, A simpler approach to coefficient regularized support vector machines regression, Stability analysis of learning algorithms for ontology similarity computation, On empirical eigenfunction-based ranking with \(\ell^1\) norm regularization, Learning by atomic norm regularization with polynomial kernels